Time series prediction with a combined GARCH (Generalized Autoregressive Conditional Heteroskedasticity) and ANN (Artificial Neural Network) Model

Abstract

GARCH models, artificial neural networks (ANN), and their hybridization.Then we applied it to real financial data to evaluate its performance. The study aims to analyze the performance of the GARCH(1, 1) model and assess its predictive accuracy compared to other models. Finally, we propose a hybrid model that combines multiple components of the previous models to further enhance predictive performance. This study contributes to a deeper understanding of how to improve the accuracy of financial volatility forecasts by using advanced and hybrid models. Keywords: GARCH; Artificial Neural Networks (ANN); Model Hybridization; Financial Volatility Forecasting; Predictive Accuracy; GARCH(1, 1) Model; ANN Linear; ANN Tanh; Hybrid Models; Advanced Financial Models.